In this article, we will explore how to use the Gemini CLI to develop a 2D English word game by integrating it with Context 7 and Task Master AI. This setup allows for efficient task management and access to the latest documentation, enhancing the development process.

Find the game demo here: Word Cloud Shooter

Following the steps below, you will learn how to set up the Gemini CLI, integrate it with Context 7, and use Task Master AI to manage tasks effectively.

Installing Gemini CLI

To install the Gemini CLI, you can use the following command:

npm install -g @upstash/gemini-cli

After installation, you can verify it by running:

gemini

Setting Up Multi-Context Processor (MCP) with Context 7

To enhance the capabilities of Augment, we can integrate it with Context 7, a Multi-Context Processor (MCP) tool. This allows Augment to access the latest documentation and coding styles from open-source projects or libraries.

To add and configure Context 7 in Augment, follow these steps:

Open the gemini settings

vim ~/.gemini/settings.json

Add the following configuration:

{
  "mcpServers": {
    "context7": {
      "command": "npx",
      "args": ["-y", "@upstash/context7-mcp"]
    }
  }
}

Installing Task Master AI

The Task Master AI is a tool that helps manage tasks and projects efficiently. It can be integrated with Augment to streamline the development process.

To install Task Master AI, you can use the following command:

npm install -g task-master-ai

After installation, next can install the task master AI MCP to Gemini CLI settings:

(Follow the task Master AI github readme: https://github.com/eyaltoledano/claude-task-master?tab=readme-ov-file#cursor--windsurf-mcpservers)

(Here should setting the one of API key for the Task Master AI, such as Anthropic, OpenAI, etc.)

{
  "mcpServers": {
    "taskmaster-ai": {
      "command": "npx",
      "args": ["-y", "--package=task-master-ai", "task-master-ai"],
      "env": {
        "ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE",
        "PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY_HERE",
        "OPENAI_API_KEY": "YOUR_OPENAI_KEY_HERE",
        "GOOGLE_API_KEY": "YOUR_GOOGLE_KEY_HERE",
        "MISTRAL_API_KEY": "YOUR_MISTRAL_KEY_HERE",
        "OPENROUTER_API_KEY": "YOUR_OPENROUTER_KEY_HERE",
        "XAI_API_KEY": "YOUR_XAI_KEY_HERE",
        "AZURE_OPENAI_API_KEY": "YOUR_AZURE_KEY_HERE",
        "OLLAMA_API_KEY": "YOUR_OLLAMA_API_KEY_HERE"
      }
    }
  }
}

Next, you can input following command to Gemini CLI to set up the Task Master AI:

Initialize taskmaster-ai in my project

This command will initialize the Task Master AI in your project, allowing you to manage tasks effectively.

Project initialized. The next step is to create tasks from a Product Requirements Document (PRD). Could you describe the project you want to build? I’ll use that to create a PRD and generate the initial tasks.

Here you can describe we don’t have a PRD, and we can use the Task Master AI to generate tasks based on the project description.

I don't have PRD document. Please create Specs.md and todolist.md according to the following specifications:

The scene begins with a basic interface where the player enters a nickname and clicks a confirm button. The background features a title, sky, and clouds. After clicking confirm, the game starts. At the bottom, there is a text input box where players can submit answers by pressing Enter. Above, there is grass and a turret, with the sky as the background and a score displayed at the top.

When the game begins, word clouds continuously fall from the sky. Clicking the turret allows the player to input text; upon submission, the turret fires a projectile. If the projectile hits a word cloud, the cloud disappears and the player scores points. The goal is to eliminate as many word clouds as possible.

If a word cloud reaches the ground without being hit, the game ends. The game record is saved locally to `result.txt` (only the top 50 scores are recorded). The final score and ranking are displayed, along with a restart button.

Next, Task Master AI will generate the Specs.md and todolist.md files based on the provided specifications.

Now, I will create a PRD file based on these specifications so I can generate the initial tasks for the project. Now that I’ve created the PRD, I will use it to generate the initial tasks for the project. Okay, I have the information I need. I will now create the tasks.json file manually. I have successfully created the tasks.json file. You can now view the tasks using the get_tasks command.

Run the following command to view the generated tasks:

get_tasks

Confirm the MCP Configuration

Open the Gemini CLI and run the following command to confirm that the MCP configuration is set up correctly:

/mcp

This command will display the current MCP configuration, including the Context 7, Tasks master AI setup.

Using gemini-cli with Context 7 and Task Master AI to Develop a 2D English Word Game

Now that you have set up the Gemini CLI with Context 7 and Task Master AI, you can use it to develop a 2D English word game. Here’s how to proceed:

Please execute the tasks and use Context 7 to search for three.js documentation to develop an English word game, referencing the latest styles and libraries from AutoGen. The roles are divided as follows:
- **Agent1**: Responsible for development and writing code, ensuring the code is well-commented for better readability.
- **Agent2**: Responsible for reviewing code quality and providing specific, actionable suggestions for improvement.
- **Agent3**: Modifies and optimizes the code based on Agent1's implementation and Agent2's suggestions, enhancing code performance and structure.
- **Agent4**: Responsible for testing game functionality, ensuring the game runs smoothly, and managing server deployment and maintenance.

This command will initiate the development process using the tasks generated by Task Master AI and Context 7 to search for the latest documentation on three.js.

Conclusion

With the Gemini CLI, Context 7, and Task Master AI set up, you can efficiently develop complex applications like a 2D English word game. The integration of these tools allows for streamlined task management, documentation access, and collaborative development, enhancing your productivity as a developer. You can now proceed with the development of your game, leveraging the capabilities of these tools to create a robust and engaging application. If you have any further questions or need assistance, feel free to ask